Somewhere, buried in one of tens of millions of cell samples, could lie the next great breakthrough in disease prevention or cure. But one of the great barriers to finding it could be the need for human eyes to evaluate a corresponding mountain of cell images, one by one. In an era when terabytes of data can be analyzed in just a few days, the opportunity to enhance automation of biomedical analysis could help researchers achieve breakthroughs faster in the treatment of almost every disease--from cancer, diabetes and rare disorders to the common cold. To spur this automation, Booz Allen Hamilton (NYSE: BAH) and Kaggle today launched the 2018 Data Science Bowl, a 90-day competition that calls on thousands of participants globally to train deep learning models to examine images of cells and identify nuclei, regardless of the experimental setup--and without human intervention. Creators of the top algorithms will split $170,000 in cash and prizes, including an NVIDIA DGX Station, a personal AI supercomputer that delivers the computing capacity of 400 CPUs in a desktop workstation.

This is the incredible moment a bubble transformed into a delicate snow globe, before freezing completely and shattering. Mesmerising footage shows a bubble balanced on a straw that quickly crystallises in sub-zero temperatures, creating a stunning swirl of delicate icy flakes. The clip captures ice crystals dancing along the fragile surface of the bubble before it collapses in on itself, all in just 14 seconds. Drone footage shows final touches being put on Apple's new campus Larry Nassar's victims confront him during his sentencing This is the incredible moment a bubble transformed into a delicate snow globe, before freezing completely and shattering. Soap bubbles are formed from three individual layers, a thin layer of water molecules between two layers of a water-based solution containing the salts of a fatty acid.

Artificial intelligence laboratories have been cropping up with increasing frequency on campuses in recent years. By and large, though, these labs have been located in computer science or electrical engineering buildings, providing a space for researchers and graduate students to develop computer algorithms that can learn or exhibit intelligent behavior. The University of Rhode Island is taking a very different approach with its new AI lab, which may be the first in the U.S. to be located in a university library. For URI, the library location is key, as officials hope that by putting the lab in a shared central place, they can bring awareness of AI to a wider swath of the university's faculty and student body. "When you have an AI lab in a specific college, the impression is that access is only for students of that college," said Karim Boughida, dean of libraries at the University of Rhode Island.

Artificial intelligence (AI) from Alibaba and Microsoft beat the human score in a Stanford reading comprehension test, the companies announced separately on Monday. The Stanford Question Answering Dataset (SQuAD) uses a set of questions and answers about Wikipedia articles, according to our sister site CNET. Microsoft scored 82.65 and Alibaba's score was 82.44, both good for first place, but barely beat the human score of 82.304. The results, however slim the margin, suggest AI may be able to match or outperform humans in certain tasks. As the field develops, this margin will most likely increase, potentially allowing AI to be smart enough to take over certain jobs--possibly even high-level ones--and let humans focus on others.

In recent years, we have become increasingly good at training deep neural networks to learn a very accurate mapping from inputs to outputs, whether they are images, sentences, label predictions, etc. from large amounts of labeled data. What our models still frightfully lack is the ability to generalize to conditions that are different from the ones encountered during training. Every time you apply your model not to a carefully constructed dataset but to the real world. The real world is messy and contains an infinite number of novel scenarios, many of which your model has not encountered during training and for which it is in turn ill-prepared to make predictions. The ability to transfer knowledge to new conditions is generally known as transfer learning and is what we will discuss in the rest of this post. Over the course of this blog post, I will first contrast transfer learning with machine learning's most pervasive and successful paradigm, supervised learning. I will then outline reasons why transfer learning warrants our attention. Subsequently, I will give a more technical definition and detail different transfer learning scenarios. I will then provide examples of applications of transfer learning before delving into practical methods that can be used to transfer knowledge.

For the first time ever, two AI systems built to process and respond to human speech (created, respectively, by Microsoft and Chinese commerce giant Alibaba) outscored humans in a reading comprehension test designed by Stanford researchers. The Stanford Question Answering Dataset, SQuAD, is composed of a staggering 100,000 questions following brief reading passages. Created in 2016, SQuAD is used as a benchmark to measure AI's progress in natural language processing. After reading excerpts from Wikipedia, the systems answer questions such as "What is the Latin name for Black Death?" and "How many actors have played Doctor Who?" Alibaba's AI score was 82.44, and Microsoft's was 82.650, with humans trailing behind them both at 82.304. Alibaba's system may have finished second, but it's more than qualified to handle its day job: Working in sales. The company's AI team reportedly works closely with the developers of Ali Xiaomi, a chat bot that answers customer questions about products.

The real power and value proposition of Apache Spark is its speed and platform to execute data processing and data science tasks. Let's see how easy it is! Packt's Video Learning Paths are a series of individual video products put together in a logical and stepwise manner such that each video builds on the skills learned in the video before it. Spark is one of the most widely-used large-scale data processing engines and runs extremely fast. It is a framework that has tools that are equally useful for application developers as well as data scientists.

When computer models designed by tech giants Alibaba and Microsoft this month surpassed humans for the first time in a reading-comprehension test, both companies celebrated the success as a historic milestone. Luo Si, the chief scientist for natural-language processing at Alibaba's AI research unit, struck a poetic note, saying, "Objective questions such as'what causes rain' can now be answered with high accuracy by machines." Teaching a computer to read has for decades been one of artificial intelligence's holiest grails, and the feat seemed to signal a coming future in which AI could understand words and process meaning with the same fluidity humans take for granted every day. But computers aren't there yet -- and aren't even really that close, said AI experts who reviewed the test results. Instead, the accomplishment highlights not just how far the technology has progressed, but also how far it still has to go. "It's a large step" for the companies' marketing "but a small step for humankind," said Oren Etzioni, chief executive of the Allen Institute for Artificial Intelligence, an AI research group funded by Microsoft co-founder Paul Allen.

We present an efficient second-order algorithm with $\tilde{O}(\frac{1}{\eta}\sqrt{T})$ regret for the bandit online multiclass problem. The regret bound holds simultaneously with respect to a family of loss functions parameterized by $\eta$, for a range of $\eta$ restricted by the norm of the competitor. The family of loss functions ranges from hinge loss ($\eta=0$) to squared hinge loss ($\eta=1$). This provides a solution to the open problem of (J. Abernethy and A. Rakhlin. An efficient bandit algorithm for $\sqrt{T}$-regret in online multiclass prediction? In COLT, 2009). We test our algorithm experimentally, showing that it also performs favorably against earlier algorithms.

The MOOC Replication Framework (MORF) is a novel software system for feature extraction, model training/testing, and evaluation of predictive dropout models in Massive Open Online Courses (MOOCs). MORF makes large-scale replication of complex machine-learned models tractable and accessible for researchers, and enables public research on privacy-protected data. It does so by focusing on the high-level operations of an extract-train-test-evaluate workflow, and enables researchers to encapsulate their implementations in portable, fully reproducible software containers which are executed on data with a known schema. MORF's workflow allows researchers to use data in analysis without providing them access to the underlying data directly, preserving privacy and data security. During execution, containers are sandboxed for security and data leakage and parallelized for efficiency, allowing researchers to create and test new models rapidly, on large-scale multi-institutional datasets that were previously inaccessible to most researchers. MORF is provided both as a Python API (the MORF Software), for institutions to use on their own MOOC data) or in a platform-as-a-service (PaaS) model with a web API and a high-performance computing environment (the MORF Platform).